How do I get my Help Scout Access Token?

You can generate an OAuth2 Access Token by creating an application in the **Help Scout Developer Portal** (developer.helpscout.com). Alternatively, if you are using a personal script, you can use the Client Credentials flow to obtain a token.

Can I add internal notes to conversations?

Yes! Use the `create_convo_note` tool. You must provide the `conversation_id` and the text of your note. This allows you to collaborate with your team without the customer seeing the message.

How do I change the status of a support thread?

Use the `update_convo_status` tool. Provide the conversation ID and the new status (active, pending, or closed). This helps you keep your mailbox organized.

Is the integration secure for managing support data?

Absolutely. The integration uses industry-standard OAuth 2.0 Bearer tokens over HTTPS. Your credentials are encrypted and stored securely within the Vinkius Cloud infrastructure.

Help Scout MCP Server for LangChain 12 tools — connect in under 2 minutes

Name: Help Scout
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 12 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Help Scout through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "help-scout": {
            "transport": "streamable_http",
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
        }
    }) as client:
        tools = client.get_tools()
        agent = create_react_agent(
            ChatOpenAI(model="gpt-4o"),
            tools,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Help Scout, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Help Scout MCP Server

Connect your Help Scout help desk to any AI agent and take full control of your customer communication and support operations through natural conversation.

LangChain's ecosystem of 500+ components combines seamlessly with Help Scout through native MCP adapters. Connect 12 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

What you can do

Conversation Oversight — List all active support threads, retrieve full transcripts, and monitor response status.
Customer Management — Access detailed customer profiles and historical interactions to provide personalized service.
Team Collaboration — Add internal notes to conversations and update statuses (active, pending, closed) directly from the chat.
Operational Visibility — List all configured mailboxes, tags, and automated workflows to ensure your help desk is correctly set up.
Performance Insights — Retrieve customer satisfaction ratings to monitor the health of your support operations.
Search Capabilities — Perform advanced searches across your entire conversation history to find answers quickly.

The Help Scout MCP Server exposes 12 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Help Scout to LangChain via MCP

Follow these steps to integrate the Help Scout MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 12 tools from Help Scout via MCP

Why Use LangChain with the Help Scout MCP Server

LangChain provides unique advantages when paired with Help Scout through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents. combine Help Scout MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Help Scout queries for multi-turn workflows

Help Scout + LangChain Use Cases

Practical scenarios where LangChain combined with the Help Scout MCP Server delivers measurable value.

RAG with live data: combine Help Scout tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Help Scout, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Help Scout tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Help Scout tool call, measure latency, and optimize your agent's performance

Help Scout MCP Tools for LangChain (12)

These 12 tools become available when you connect Help Scout to LangChain via MCP:

create_convo_note

Use this for team collaboration. Add a private note to a conversation

get_conversation

Get detailed information about a specific conversation

get_customer

Get detailed profile information for a specific customer

list_conversations

Useful for monitoring incoming customer queries. List support conversations/tickets

list_customer_ratings

List recent customer satisfaction ratings

list_customers

List all customers registered in the help desk

list_mailboxes

List all configured support mailboxes

list_staff_users

List all support agents/users in the tenant

list_tags

List all available tags for categorizing conversations

list_workflows

List automated support workflows

search_conversations

Search for conversations using a query

update_convo_status

Change the status of a conversation (e.g., active, closed)

Example Prompts for Help Scout in LangChain

Ready-to-use prompts you can give your LangChain agent to start working with Help Scout immediately.

"List all active conversations in the 'Main' mailbox."

"Search for conversations from 'john.doe@example.com'."

"Add an internal note to conversation ID 12345: 'Confirmed with engineering, fix arriving tomorrow'."

Troubleshooting Help Scout MCP Server with LangChain

Common issues when connecting Help Scout to LangChain through the Vinkius, and how to resolve them.

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Help Scout + LangChain FAQ

Common questions about integrating Help Scout MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.